We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions due to different camera viewpoints and clutter. We propose a three-phase framework to fine-tune existing captioning models that enhances caption accuracy and consistency across views via a consensus mechanism. First, an agent explores the environment, collecting noisy image-caption pairs. Then, a consistent pseudo-caption for each object instance is distilled via consensus using a large language model. Finally, these pseudo-captions are used to fine-tune an off-the-shelf captioning model, with the addition of contrastive learning. We analyse the performance of the combination of captioning models, exploration policies, pseudo-labeling methods, and fine-tuning strategies, on our manually labeled test set. Results show that a policy can be trained to mine samples with higher disagreement compared to classical baselines. Our pseudo-captioning method, in combination with all policies, has a higher semantic similarity compared to other existing methods, and fine-tuning improves caption accuracy and consistency by a significant margin. Code and test set annotations available at this https URL

We present a comprehensive framework for studying and leveraging morphological symmetries in robotic systems. These are intrinsic properties of the robot's morphology, frequently observed in animal biology and robotics, which stem from the replication of kinematic structures and the symmetrical distribution of mass. We illustrate how these symmetries extend to the robot's state space and both proprioceptive and exteroceptive sensor measurements, resulting in the equivariance of the robot's equations of motion and optimal control policies. Thus, we recognize morphological symmetries as a relevant and previously unexplored physics-informed geometric prior, with significant implications for both data-driven and analytical methods used in modeling, control, estimation and design in robotics. For data-driven methods, we demonstrate that morphological symmetries can enhance the sample efficiency and generalization of machine learning models through data augmentation, or by applying equivariant/invariant constraints on the model's architecture. In the context of analytical methods, we employ abstract harmonic analysis to decompose the robot's dynamics into a superposition of lower-dimensional, independent dynamics. We substantiate our claims with both synthetic and real-world experiments conducted on bipedal and quadrupedal robots. Lastly, we introduce the repository MorphoSymm to facilitate the practical use of the theory and applications outlined in this work.

We present a new fully automatic block-decomposition hexahedral meshing algorithm capable of producing high quality meshes that strictly preserve feature curve networks on the input surface and align with an input surface cross-field. We produce all-hex meshes on the vast majority of inputs, and introduce localized non-hex elements only when the surface feature network necessitates those. The input to our framework is a closed surface with a collection of geometric or user-demarcated feature curves and a feature-aligned surface cross-field. Its output is a compact set of blocks whose edges interpolate these features and are loosely aligned with this cross-field. We obtain this block decomposition by cutting the input model using a collection of simple cutting surfaces bounded by closed surface loops. The set of cutting loops spans the input feature curves, ensuring feature preservation, and is obtained using a field-space sampling process. The computed loops are uniformly distributed across the surface, cross orthogonally, and are loosely aligned with the cross-field directions, inducing the desired block decomposition. We validate our method by applying it to a large range of complex inputs and comparing our results to those produced by state-of-the-art alternatives. Contrary to prior approaches, our framework consistently produces high-quality field aligned meshes while strictly preserving geometric or user-specified surface features.

Critical Raw Materials (CRMs) such as copper, manganese, gallium, and various rare earths have great importance for the electronic industry. To increase the concentration of individual CRMs and thus make their extraction from Waste Printed Circuit Boards (WPCBs) convenient, we have proposed a practical approach that involves selective disassembling of the different types of electronic components from WPCBs using mechatronic systems guided by artificial vision techniques. In this paper we evaluate the real-time accuracy of electronic component detection and localization of the Real-Time DEtection TRansformer model architecture. Transformers have recently become very popular for the extraordinary results obtained in natural language processing and machine translation. Also in this case, the transformer model achieves very good performances, often superior to those of the latest state of the art object detection and localization models YOLOv8 and YOLOv9.

We prove a homogeneous, quantitative version of Ehrling's inequality for the function spaces $H^1(\Omega)\subset\subset L^2(\partial\Omega)$, $H^1(\Omega)\hookrightarrow L^2(\Omega)$ which reflects geometric properties of a given $C^{1,1}$-domain $\Omega\subset\mathbb{R}^n$. We use this result to derive quantitative homogeneous versions of Gaffney's inequality, of relevance in electromagnetism as well as Korn's inequality, of relevance in elasticity theory. The main difference to the corresponding classical results is that the constants appearing in our inequalities turn out to be dimensional constants. We provide explicit upper bounds for these constants and show that in the case of the tangential homogeneous Korn inequality our upper bound is asymptotically sharp as $n\rightarrow \infty$. Lastly, we raise the question of the optimal values of these dimensional constants.

We present an avatar system designed to facilitate the embodiment of humanoid robots by human operators, validated through iCub3, a humanoid developed at the Istituto Italiano di Tecnologia (IIT). More precisely, the contribution of the paper is twofold: first, we present the humanoid iCub3 as a robotic avatar which integrates the latest significant improvements after about fifteen years of development of the iCub series; second, we present a versatile avatar system enabling humans to embody humanoid robots encompassing aspects such as locomotion, manipulation, voice, and face expressions with comprehensive sensory feedback including visual, auditory, haptic, weight, and touch modalities. We validate the system by implementing several avatar architecture instances, each tailored to specific requirements. First, we evaluated the optimized architecture for verbal, non-verbal, and physical interactions with a remote recipient. This testing involved the operator in Genoa and the avatar in the Biennale di Venezia, Venice - about 290 Km away - thus allowing the operator to visit remotely the Italian art exhibition. Second, we evaluated the optimised architecture for recipient physical collaboration and public engagement on-stage, live, at the We Make Future show, a prominent world digital innovation festival. In this instance, the operator was situated in Genoa while the avatar operates in Rimini - about 300 Km away - interacting with a recipient who entrusted the avatar a payload to carry on stage before an audience of approximately 2000 spectators. Third, we present the architecture implemented by the iCub Team for the ANA Avatar XPrize competition.

Deep neural networks have been extensively applied in the medical domain for various tasks, including image classification, segmentation, and landmark detection. However, their application is often hindered by data scarcity, both in terms of available annotations and images. This study introduces a novel application of denoising diffusion probabilistic models (DDPMs) to the landmark detection task, specifically addressing the challenge of limited annotated data in x-ray imaging. Our key innovation lies in leveraging DDPMs for self-supervised pre-training in landmark detection, a previously unexplored approach in this domain. This method enables accurate landmark detection with minimal annotated training data (as few as 50 images), surpassing both ImageNet supervised pre-training and traditional self-supervised techniques across three popular x-ray benchmark datasets. To our knowledge, this work represents the first application of diffusion models for self-supervised learning in landmark detection, which may offer a valuable pre-training approach in few-shot regimes, for mitigating data scarcity.

Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size datasets. However, experimental setups are often not reproducible, thus leading to unfair and inconsistent comparisons. In this work, we benchmark these methods under a reproducible setup on two single objects scenarios, tabletop without occlusions and hand-held containers, to facilitate future comparisons. We include a version of a recent architecture, Mask2Former, re-trained for affordance segmentation and show that this model is the best-performing on most testing sets of both scenarios. Our analysis shows that models are not robust to scale variations when object resolutions differ from those in the training set.

Despite explainable AI (XAI) has recently become a hot topic and several different approaches have been developed, there is still a widespread belief that it lacks a convincing unifying foundation. On the other hand, over the past centuries, the very concept of explanation has been the subject of extensive philosophical analysis in an attempt to address the fundamental question of "why" in the context of scientific law. However, this discussion has rarely been connected with XAI. This paper tries to fill in this gap and aims to explore the concept of explanation in AI through an epistemological lens. By comparing the historical development of both the philosophy of science and AI, an intriguing picture emerges. Specifically, we show that a gradual progression has independently occurred in both domains from logical-deductive to statistical models of explanation, thereby experiencing in both cases a paradigm shift from deterministic to nondeterministic and probabilistic causality. Interestingly, we also notice that similar concepts have independently emerged in both realms such as, for example, the relation between explanation and understanding and the importance of pragmatic factors. Our study aims to be the first step towards understanding the philosophical underpinnings of the notion of explanation in AI, and we hope that our findings will shed some fresh light on the elusive nature of XAI.

Measuring grasp stability is an important skill for dexterous robot manipulation tasks, which can be inferred from haptic information with a tactile sensor. Control policies have to detect rotational displacement and slippage from tactile feedback, and determine a re-grasp strategy in term of location and force. Classic stable grasp task only trains control policies to solve for re-grasp location with objects of fixed center of gravity. In this work, we propose a revamped version of stable grasp task that optimises both re-grasp location and gripping force for objects with unknown and moving center of gravity. We tackle this task with a model-free, end-to-end Transformer-based reinforcement learning framework. We show that our approach is able to solve both objectives after training in both simulation and in a real-world setup with zero-shot transfer. We also provide performance analysis of different models to understand the dynamics of optimizing two opposing objectives.

The star-forming main sequence (SFMS) is a tight relation observed between stellar masses and star formation rates (SFR) in a population of galaxies. This relation is observed at different redshifts, in various morphological, and environmental domains, and is key to understanding the underlying relations between a galaxy budget of cold gas and its stellar content. Euclid Quick Data Release 1 (Q1) gives us the opportunity to investigate this fundamental relation in galaxy formation and evolution. We complement the Euclid release with public IRAC observations of the Euclid Deep Fields, improving the quality of recovered photometric redshifts, stellar masses, and SFRs, as is shown both with simulations and a comparison with available spectroscopic redshifts. From Q1 data alone, we recover more than $\sim 30\,\mathrm{k}$ galaxies with $\log_{10} (M_\ast/M_\odot) > 11$, giving a precise constraint of the SFMS at the high-mass end. We investigated the SFMS, in a redshift interval between $0.2$ and $3.0$, comparing our results with the existing literature and fitting them with a parameterisation taking into account the presence of a bending of the relation at the high-mass end, depending on the bending mass, $M_0$. We find good agreement with previous results in terms of $M_0$ values, and an increasing trend for the relation scatter at higher stellar masses. We also investigate the distribution of physical (e.g. dust absorption, $A_V$, and formation age) and morphological properties (e.g., Sérsic index and radius) in the SFR--stellar mass plane, and their relation with the SFMS. These results highlight the potential of Euclid in studying the fundamental scaling relations that regulate galaxy formation and evolution in anticipation of the forthcoming Data Release 1.

Exotic hadrons are a new class of hadronic states whose properties do not allow them to be classified as conventional quark-antiquark mesons or three quark baryons. Finding new and understanding established exotic states is the most important topic in today's hadron spectroscopy and a promising avenue to advance our knowledge on Quantum Chromodynamics in the non-perturbative regime. While several high-quality reviews on the topic exist, they are all at an advanced level. The present article aims to address new-comers to the field with a simple introduction to exotic hadrons with an emphasis on the experimental studies.

Context: The detection of the highest energy neutrino observed to date by KM3NeT, with an estimated energy of 220 PeV, opens up new possibilities for the study and identification of the astrophysical sources responsible for a diffuse flux of such ultra-high-energy neutrinos, among which gamma-ray bursts are longstanding candidates. Aims: Based on the event KM3-230213A, we derive constraints on the baryon loading and density of the surrounding environment in models of blastwaves in long-duration gamma-ray bursts. Methods: We compute the diffuse flux from gamma-ray burst blastwaves, either expanding in a constant density interstellar medium or developing in a radially decreasing density of a wind-like environment surrounding the gamma-ray burst progenitor star, by taking into account the expected neutrino spectra and luminosity function. We use a Poisson likelihood method to constrain the blastwave model parameters by calculating the expected number of neutrino events within the 90% confidence level energy range of KM3-230213A and by using the joint exposure of KM3NeT/ARCA, IceCube and Pierre Auger. Results: We constrain the baryon loading to be $\leq \{392, 131, 39, 13\}$ at 90% confidence level, which is inversely proportional to a varying interstellar medium particle density of $\{1, 3, 10, 30\}$ cm$^{-3}$. In the wind-like environment case, the baryon loading is $\leq \{20, 50, 100\}$ at 90% confidence level, which is proportional to the sixth power of a varying density parameter of $\{0.05, 0.06, 0.07\}$.

Physics-informed neural network (PINN) is a data-driven solver for partial and ordinary differential equations(ODEs/PDEs). It provides a unified framework to address both forward and inverse problems. However, the complexity of the objective function often leads to training failures. This issue is particularly prominent when solving high-frequency and multi-scale problems. We proposed using transfer learning to boost the robustness and convergence of training PINN, starting training from low-frequency problems and gradually approaching high-frequency problems. Through two case studies, we discovered that transfer learning can effectively train PINN to approximate solutions from low-frequency problems to high-frequency problems without increasing network parameters. Furthermore, it requires fewer data points and less training time. We elaborately described our training strategy, including optimizer selection, and suggested guidelines for using transfer learning to train neural networks for solving more complex problems.

Turbulence is indispensable to redistribute nutrients for all life forms larger than microbial, on land and in the ocean. Yet, the development of deep-sea turbulence has not been studied in three dimensions (3D). As a disproportionate laboratory, an array of nearly 3000 high-resolution temperature sensors had been installed for three years on the flat 2500-m deep bottom of the Mediterranean Sea. The time series from the half-cubic hectometer 3D mooring-array allows for the creation of unique movies of deep-sea water motions. Although temperature differences are typically 0.001degrC, variable convection-turbulence is observed as expected from geothermal heating through the flat seafloor. During about 40% of the time, an additional turbulence, 3 times stronger in magnitude, is observed from slantwise advected warmer waters to pass in turbulent clouds. Besides turbulent clouds and seafloor heating, movies also reveal weakly turbulent interfacial-wave breakdown that commonly occurs in the open ocean far away from boundaries.

Condition monitoring subsea pipelines in low-visibility underwater environments poses significant challenges due to turbidity, light distortion, and image degradation. Traditional visual-based inspection systems often fail to provide reliable data for mapping, object recognition, or defect detection in such conditions. This study explores the integration of advanced artificial intelligence (AI) techniques to enhance image quality, detect pipeline structures, and support autonomous fault diagnosis. This study conducts a comparative analysis of two most robust versions of YOLOv8 and Yolov11 and their three variants tailored for image segmentation tasks in complex and low-visibility subsea environments. Using pipeline inspection datasets captured beneath the seabed, it evaluates model performance in accurately delineating target structures under challenging visual conditions. The results indicated that YOLOv11 outperformed YOLOv8 in overall performance.